Research map / Point clouds / Shape and surface completion
3DDM: Physically-based Anisotropic 3D Diffusion Model with 3D Gaussian for Point Cloud Completion
Long Xi, Jia Ma, ZhenYu Yuan, Tao Xue, Wen Tang, Wen Lv
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use 20 diffusion steps instead of 1 (ablation) | 3DDM · ShapeNet34 guitar | CD-S: 7.89 -> 1.05 | Improved |
| use 100 instead of 800 diffusion steps (ablation) | 3DDM · ShapeNet34 guitar | CD-S: 1.20 -> 1.01 | Improved |
| use 20 instead of 100 diffusion steps (ablation) | 3DDM · ShapeNet34 guitar | F1-S: 0.61 -> 0.60 | No clear effect |
| use DGCNN instead of PointNet++ encoder (ablation) | 3DDM · ShapeNet34 guitar | F1-S: 0.65 -> 0.83 | Improved |
| use DGCNN instead of PointNet encoder (ablation) | 3DDM · ShapeNet34 guitar | F1-S: 0.82 -> 0.83 | No clear effect |
| use 3DDM instead of AnchorFormer | 3DDM · ShapeNet21 unseen | F1-S: 0.26 -> 0.37 | Improved |
| use 3DDM instead of AnchorFormer | 3DDM · ShapeNet34 seen | CD-H: 1.76 -> 1.90 | Hurt |
| use 3DDM instead of AnchorFormer | 3DDM · ShapeNet21 unseen | CD-S: 1.61 -> 1.72 | Hurt |
| use 3DDM instead of FSC | 3DDM · KITTI | MMD: 1.25 -> 0.07 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AnchorFormer — AnchorFormer: Point Cloud Completion From Discriminative Nodes (CVPR 2023) · better on 9 of 11 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization (CVPR 2025 · similarity 0.87)
- Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates (NeurIPS 2025 · similarity 0.87)
- ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors (ICLR 2025 · similarity 0.87)
- Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion (CVPR 2024 · similarity 0.87)
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images (CVPR 2025 · similarity 0.87)
- 3DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
